Phoenix-bench shows agentic AI systems lose 37-58% resolved rate when moving from SWE-bench Verified to hardware tasks because bugs spread across parallel modules via signal flow, with testbench feedback lifting performance by 42-45% while file-level oracles add only 1.4%.
Insights from rights and wrongs: A large language model for solving assertion failures in rtl design,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AR 2representative citing papers
UVM^2 is an LLM-driven system that generates and refines UVM testbenches for RTL verification, reporting up to substantial time savings and average code/function coverage of 87.44%/89.58% on designs up to 1.6K lines, outperforming prior methods.
citing papers explorer
-
Is Agentic AI Ready for Real-World Hardware Engineering? A Deep Dive with Phoenix-bench
Phoenix-bench shows agentic AI systems lose 37-58% resolved rate when moving from SWE-bench Verified to hardware tasks because bugs spread across parallel modules via signal flow, with testbench feedback lifting performance by 42-45% while file-level oracles add only 1.4%.
-
From Concept to Practice: an Automated LLM-aided UVM Machine for RTL Verification
UVM^2 is an LLM-driven system that generates and refines UVM testbenches for RTL verification, reporting up to substantial time savings and average code/function coverage of 87.44%/89.58% on designs up to 1.6K lines, outperforming prior methods.